INDEX

Explanations

rankings or positions related to military or organizational structures

oai_token-act-pair · gpt-3.5-turbo

references to different ranks or titles within military or organizational contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

dos

-0.75

izon

-0.72

âĶģ

-0.70

Ti

-0.68

tera

-0.66

rise

-0.66

gp

-0.65

 Timber

-0.64

creen

-0.64

MED

-0.63

POSITIVE LOGITS

 corps

0.97

 officer

0.89

ially

0.86

utenant

0.84

geant

0.77

å£«

0.77

 officers

0.77

 colonel

0.76

 emer

0.74

holder

0.69

Activations Density 0.034%

rankings or positions related to military or organizational structures

references to different ranks or titles within military or organizational contexts

No Known Activations